A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Study compares methods for treatment assignment, finding A-learner best for playlist generation.
Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.
We address the challenge of designing optimal adversarial noise algorithms for settings where a learner has access to multiple classifiers. We demonstrate how this problem can be framed as finding strategies at equilibrium in a two-player, zero-sum game between a learner and an adversary. In doing so, we illustrate the…
New HPO frameworks needed for continual learning.
Proves efficient learning of hierarchical structure in meta-reinforcement learning.
A new learning method for prosthetic arms without explicit rewards.
New algorithm optimally identifies best arm in both stochastic and adversarial settings.
The Predictive Normalized Maximum Likelihood (pNML) scheme has been recently suggested for universal learning in the individual setting, where both the training and test samples are individual data. The goal of universal learning is to compete with a ``genie'' or reference learner that knows the data values, but is res…
In a typical online learning scenario, a learner is required to process a large data stream using a small memory buffer. Such a requirement is usually in conflict with a learner's primary pursuit of prediction accuracy. To address this dilemma, we introduce a novel Bayesian online classi cation algorithm, called the Vi…
New framework for understanding adversarial and stochastic learning.
We develop a new model and algorithms for machine learning-based learning analytics, which estimate a learner's knowledge of the concepts underlying a domain, and content analytics, which estimate the relationships among a collection of questions and those concepts. Our model represents the probability that a learner p…
Algorithm improves RL model selection for repeated games with utility maximization.
We study the query complexity of a learner-private sequential learning problem, motivated by the privacy and security concerns due to eavesdropping that arise in practical applications such as pricing and Federated Learning. A learner tries to estimate an unknown scalar value, by sequentially querying an external datab…
We call a learner super-teachable if a teacher can trim down an iid training set while making the learner learn even better. We provide sharp super-teaching guarantees on two learners: the maximum likelihood estimator for the mean of a Gaussian, and the large margin classifier in 1D. For general learners, we provide a …
A new model for sequential prediction handles adversarial examples by allowing abstention.
The construction by Du et al. (2019) implies that even if a learner is given linear features in that approximate the rewards in a bandit with a uniform error of , then searching for an action that is optimal up to requires examining essentially all actions. We use the Kiefer-Wolfowitz theorem to…
When consequential decisions are informed by algorithmic input, individuals may feel compelled to alter their behavior in order to gain a system's approval. Models of agent responsiveness, termed "strategic manipulation," analyze the interaction between a learner and agents in a world where all agents are equally able …
Learning from positive and unlabeled data or PU learning is the setting where a learner only has access to positive examples and unlabeled data. The assumption is that the unlabeled data can contain both positive and negative examples. This setting has attracted increasing interest within the machine learning literatur…
Most machine learning theory and practice is concerned with learning a single task. In this thesis it is argued that in general there is insufficient information in a single task for a learner to generalise well and that what is required for good generalisation is information about many similar learning tasks. Similar …
We analyze the sample complexity of learning from multiple experiments where the experimenter has a total budget for obtaining samples. In this problem, the learner should choose a hypothesis that performs well with respect to multiple experiments, and their related data distributions. Each collected sample is associat…
Recent work has demonstrated that problems-- particularly imitation learning and structured prediction-- where a learner's predictions influence the input-distribution it is tested on can be naturally addressed by an interactive approach and analyzed using no-regret online learning. These approaches to imitation learni…
Quantum machine learning can't achieve polylogarithmic runtimes, even with quantum data access.
Paper tackles continual learning with single-index models, proving regret bounds.
New neural methods for stable control with provable guarantees.
New learner achieves optimal agnostic error in small error regime.
How many bits of information are revealed by a learning algorithm for a concept class of VC-dimension ? Previous works have shown that even for the amount of information may be unbounded (tend to with the universe size). Can it be that all concepts in the class require leaking a large amount of inform…
We consider the problem of online combinatorial optimization under semi-bandit feedback, where a learner has to repeatedly pick actions from a combinatorial decision set in order to minimize the total losses associated with its decisions. After making each decision, the learner observes the losses associated with its a…
Machine learning refactors knowledge to improve learning efficiency.
We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine a scalar value, , by sequentially querying an external database and receiving binary responses. In the meantime, an adversary observes…
Study adversarial perturbations in classification, analyzing learning and certification.
Hyperparameters are critical in machine learning, as different hyperparameters often result in models with significantly different performance. Hyperparameters may be deemed confidential because of their commercial value and the confidentiality of the proprietary algorithms that the learner uses to learn them. In this …
Rank regression from pairwise comparisons requires many comparisons to accurately learn model parameters.
The nearest neighbor rule is proven consistent in a broad setting.
Plotting a learner's average performance against the number of training samples results in a learning curve. Studying such curves on one or more data sets is a way to get to a better understanding of the generalization properties of this learner. The behavior of learning curves is, however, not very well understood and…
A basic problem in machine learning is to find a mapping from a low dimensional latent space to a high dimensional observation space . Modern tools such as deep neural networks are capable to represent general non-linear mappings. A learner can easily find a mapping which perfectly fits a…
For many interesting tasks, such as medical diagnosis and web page classification, a learner only has access to some positively labeled examples and many unlabeled examples. Learning from this type of data requires making assumptions about the true distribution of the classes and/or the mechanism that was used to selec…
Transductive learning considers situations when a learner observes labelled training points and unlabelled test points with the final goal of giving correct answers for the test points. This paper introduces a new complexity measure for transductive learning called Permutational Rademacher Complexity (PRC) and …
We study the problem of online influence maximization in social networks. In this problem, a learner aims to identify the set of "best influencers" in a network by interacting with it, i.e., repeatedly selecting seed nodes and observing activation feedback in the network. We capitalize on an important property of the i…
We address the problem of regret minimization in logistic contextual bandits, where a learner decides among sequential actions or arms given their respective contexts to maximize binary rewards. Using a fast inference procedure with Polya-Gamma distributed augmentation variables, we propose an improved version of Thomp…
We present a comprehensive study of the use of generative modeling approaches for Multiple-Instance Learning (MIL) problems. In MIL a learner receives training instances grouped together into bags with labels for the bags only (which might not be correct for the comprised instances). Our work was motivated by the task …
F-PACOH improves meta-learners' reliability in uncertain regions.
New algorithm reduces clustering cost in bandit feedback.
We study an online decision making problem where on each round a learner chooses a list of items based on some side information, receives a scalar feedback value for each individual item, and a reward that is linearly related to this feedback. These problems, known as contextual semibandits, arise in crowdsourcing, rec…
The ERI is a new index for measuring exam readiness.
Optimal bounds on regret and constraint violation in adversarial COCO.
Paper tackles dense subgraph discovery with noisy feedback.
New algorithm minimizes cumulative loss in dynamic linear bandits without prior knowledge of comparator switches.
New algorithm allows IGL to work with action-inclusive feedback.